European Medicines Agency gives first green light to AI use citing liver biopsy trial

The European Medicines Agency (EMA) gave its approval to an artificial intelligence diagnostic tool for the first time on Friday, saying pathologists can benefit from using AI to analyze liver biopsy scans. The Amsterdam-based agency’s Human Medicines Committee emphasized that doctors will still be responsible for their final diagnosis, and that they will be allowed to reject the conclusions given by the AI tool known as AIM-NASH.

The system was developed to recognize the severity of liver inflammation unrelated to alcohol use, known as MASH, or metabolic dysfunction associated steatohepatitis. The AI-based system that employs a “machine learning model trained on more than 100,000 annotations from 59 pathologists who assessed over 5,000 liver biopsies across nine large clinical trials,” the EMA said.

MASH is caused by fat building up in the liver, leading to inflammation, irritation, and scarring, and is linked to type 2 diabetes, obesity, abnormal cholesterol, high blood pressure, and belly fat. “If untreated, it can lead to advanced liver disease,” the committee said. Patients who suffer from this are often tired and have weak muscles as a result.

The EMA committee agreed that the tool can help increase dependability and repeatability. They also feel doctors can accept information from the tool as scientifically valid.

EMA has said that the use of the AI system will result in a reduction in differences in opinion which arise among specialists under the current system. During a trial, liver biopsy sections were discussed by three independent pathologists who reviewed the tissue to determine the degree of inflammation.

“These biopsies are the gold standard for demonstrating the efficacy of new, investigational medicines. However, high variability in MASH/NASH clinical trials is a challenge, as specialists who review biopsy samples may not always agree on the severity of inflammation or scarring.”

The EMA said it believes this advancement can also lead to researchers being able to gather clearer evidence and draw new conclusions based on future clinical trials that include fewer patients.